PENDETEKSI OBJEK PADA ROBOT BERGERAK OTONOM DENGAN METODE GEOMETRI MOMENTS INVARIANT DAN JST

SEGARA, BAYU RASA and Nurmaini, Siti (2018) PENDETEKSI OBJEK PADA ROBOT BERGERAK OTONOM DENGAN METODE GEOMETRI MOMENTS INVARIANT DAN JST. Master thesis, Sriwijaya University.

Preview	Text RAMA_56201_09111001011_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (357kB) | Preview
	Text RAMA_56201_09111001011_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (473kB) | Request a copy
	Text RAMA_56201_09111001011_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (228kB) | Request a copy
	Text RAMA_56201_09111001011_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (616kB) | Request a copy
	Text RAMA_56201_09111001011_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (26kB) | Request a copy
	Text RAMA_56201_09111001011_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (29kB) | Request a copy

Abstract

Mobile robot is research field which many researcher make innovation to make robot more perfect and close to human ability, one of them is to see and recognize the object. Robot use geometry moments invariant and artificial neural network backpropagation in this research so mobile robot can recognize object cube, pyramid, and ball. Geometry moment invariant is one of methods on image processing which can identify object to characterize target object with other object. Artificial neural network is a methods to introduction pattern where does it work is like human brain to get information and learning. On the test result which has been done in this research, the result obtained on the introduction of trained data with accuracy 100% and realtime testing by taking distance 40cm can get 100% accuracy, on testing with distance 80cm can get 66,67% accuracy, while testing with distance 120cm can get 30% accuracy. Robot movement with realtime testing can work perfectly and when robot is given ball obstacle then robot will be stop, when it is given pyramid obstacle then robot will move to the right and it will move to the left if there is a cube obstacle in front of the robot, robot will move straight forward when it doesn’t detect obstacle in front of it.

Item Type:	Thesis (Master)
Uncontrolled Keywords:	Raspberry Pi, Thresholding, Geometry Moments Invariant, Artificial Neural Network, Backpropagation.
Subjects:	Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.E94 Computer system performance. Computer Communication Networks. Computer science. Logic design. Operating systems (Computers).
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Mrs Sri Astuti
Date Deposited:	23 Sep 2019 04:05
Last Modified:	23 Sep 2019 04:05
URI:	http://repository.unsri.ac.id/id/eprint/8533

Actions (login required)

View Item